Safety early warning method, device and equipment for long-time driving and storage medium

Abstract

The invention relates to the technical field of auxiliary driving, and discloses a safety early warning method and device for long-time driving, equipment and a storage medium. According to the technical scheme, the state information set corresponding to the current state information in the preset classification model can be determined as the target state information set according to the current state information corresponding to the current driver, and the early warning instruction is output according to the early warning processing mode corresponding to the target state information set. And according to the early warning instruction, controlling and outputting an early warning prompt, and controlling a vehicle cabin system. Therefore, early warning reminding for a driver and early warning operation for controlling the vehicle cabin system are realized. The whole process does not need manual operation of the driver, health early warning and management of the driver are automatically achieved, and driving potential safety hazards caused by body health of the driver are avoided.

Description

Technical Field

[0001] The present application relates to the field of assisted driving technology, and in particular to a safety warning method, device, computer equipment and storage medium for long-term driving. Background Art

[0002] With the development of society, cars have become an indispensable means of transportation in people's daily lives, and driving safety and driver health issues have received more and more attention. Long-term driving can cause physical fatigue and discomfort to drivers, such as back pain, chronic prostate disease, etc. These problems not only affect the driver's physical health, but may also affect the driver's driving safety.

[0003] Therefore, it is necessary to provide a method for timely providing a safety warning to the driver to avoid driving safety hazards caused by the driver's physical health. Summary of the invention

[0004] In view of the above problems, the present application provides a long-time driving safety warning method, device, equipment and storage medium, which are used to solve the technical problem in the prior art that drivers suffer from physical discomfort due to long-time driving, thereby affecting driving safety.

[0005] By determining the state information set corresponding to the current state information in the preset classification model as the target state information set according to the current state information corresponding to the current driver, outputting a warning instruction according to the warning processing method corresponding to the target state information set, and controlling the output of the warning reminder and the vehicle cockpit system according to the warning instruction, the warning operation of the driver's warning reminder and the control of the vehicle cockpit system is realized.

[0006] According to one aspect of an embodiment of the present application, a safety warning method for long-term driving is provided, the method comprising: obtaining current state information corresponding to a current driver; wherein the current state information comprises physical state information and driving state information of the current driver, and vehicle driving state information; determining that a state information set corresponding to the current state information in a preset classification model is a target state information set; wherein the preset classification model comprises a plurality of state information sets, each of the state information sets comprises a plurality of historical state information of the same type, and each of the state information sets corresponds to a warning processing method; outputting a warning instruction according to the warning processing method corresponding to the target state information set, and controlling the output of a warning reminder according to the warning instruction, and controlling the vehicle cockpit system.

[0007] In an optional manner, the method further includes: using the physical state information, the driving state information, and the vehicle driving state information as coordinate axes of different dimensions, respectively, to construct an initial coordinate system; drawing coordinate points corresponding to each historical state information in the initial coordinate system according to the historical state information of the current driver; determining multiple clusters in the initial coordinate system according to the multiple coordinate points drawn; wherein each cluster corresponds to a state information set, and the categories of historical state information in the same state information set are the same; constructing the preset classification model based on the initial coordinate system and the multiple clusters, and presetting a corresponding early warning processing method for each cluster.

[0008] In an optional manner, the method of determining multiple clusters in the initial coordinate system based on the multiple coordinate points obtained by drawing further includes: if the number of coordinate points in the designated spatial area is a preset number, taking the designated spatial area as a designated cluster; wherein the designated spatial area is any spatial area of ​​a fixed size in the initial coordinate system; taking the historical status information corresponding to the coordinate points in the designated spatial area as status information of the same category to constitute a designated status information set corresponding to the designated cluster, so as to obtain multiple clusters in the initial coordinate system, and a status information set corresponding to each cluster.

[0009] In an optional manner, the preset classification model is a coordinate system in which there are multiple clusters, and each cluster corresponds to a corresponding state information set; the determination of the state information set corresponding to the current state information in the preset classification model as the target state information set further includes: determining the target coordinate point corresponding to the current state information in the coordinate system, and calculating the center distance value between the target coordinate point and each cluster; taking the cluster corresponding to the minimum center distance value as the target cluster corresponding to the target coordinate point, and taking the state information set represented by the target cluster as the target state information set.

[0010] In an optional manner, determining the target coordinate point corresponding to the current state information in the coordinate system further includes: digitizing the body state information, the driving state information, and the vehicle driving state information in the current state information to obtain three values; and tracing points in the coordinate system based on the three values ​​to determine the target coordinate point corresponding to the current state information in the coordinate system.

[0011] In an optional manner, before obtaining the current status information corresponding to the current driver, the method also includes: determining the physical status information of the current driver based on the collected physiological parameters of the current driver; sending the collected facial image frame of the current driver to an external analysis end, so that the external analysis end determines the driving status information of the current driver based on the facial image frame, and enables the external analysis end to feed back the driving status information; determining the vehicle driving status information based on the posture change information, driving trajectory, turn signal information, and braking frequency of the current vehicle.

[0012] In an optional manner, there are multiple target status information sets; outputting a warning instruction according to the warning processing method corresponding to the target status information set further includes: fusing the warning processing methods corresponding to each target information set, and deduplicating the fused warning processing method; outputting a warning instruction according to the deduplicated fused warning processing method; wherein the warning instruction carries warning text, and a mode adjustment strategy for seats and air conditioners in a vehicle cabin system; controlling the output of the warning reminder and controlling the vehicle cabin system according to the warning instruction further includes: displaying and playing the warning text, and adjusting the seats and air conditioners according to the mode adjustment strategy.

[0013] According to another aspect of an embodiment of the present application, a safety warning device for long-term driving is provided, including: an information acquisition module, used to obtain current state information corresponding to the current driver; wherein the current state information includes the physical state information and driving state information of the current driver, and the vehicle driving state information; a set determination module, used to determine that the state information set corresponding to the current state information in a preset classification model is a target state information set; wherein the preset classification model includes multiple state information sets, each of the state information sets includes multiple historical state information of the same type, and each of the state information sets corresponds to a warning processing method; a warning module, used to output a warning instruction according to the warning processing method corresponding to the target state information set, and control the output of the warning reminder according to the warning instruction, and control the vehicle cabin system.

[0014] According to another aspect of an embodiment of the present application, a computer device is provided, including: a controller; and a memory for storing one or more programs, wherein when the one or more programs are executed by the controller, the controller implements the safety warning method for long-term driving as described in any one of the above claims.

[0015] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein at least one executable instruction is stored in the storage medium. When the executable instruction is executed on a computer device / equipment, the computer device / equipment performs the operation of the long-term driving safety warning method as described in any one of the above claims.

[0016] The embodiment of the present application determines the state information set corresponding to the current state information in the preset classification model as the target state information set according to the current state information corresponding to the current driver, outputs a warning instruction according to the warning processing method corresponding to the target state information set, and controls the output of the warning reminder according to the warning instruction, as well as controls the vehicle cockpit system. The warning reminder for the driver and the warning operation of controlling the vehicle cockpit system are realized. The whole process does not require manual operation by the driver, and automatically realizes the health warning and management of the driver, avoiding driving safety hazards caused by the driver's physical health.

[0017] At the same time, since the current status information corresponding to the current driver is obtained in real time, and the corresponding warning instructions are also automatically generated in real time, compared with the existing technology that requires the driver to monitor and activate it independently, the safety warning of this solution is more timely and runs through the entire driving process of the driver. It is also more comprehensive, so it can be more preventive and can provide warnings and adjustments before further serious health problems are caused, avoiding poor warning effects caused by intervention after long-term driving.

[0018] Moreover, through the preset classification model, the target state information set corresponding to the current state information can be quickly determined, and the corresponding warning processing method can be further quickly determined, so that the warning instruction can be output in time according to the corresponding warning processing method, and the warning reminder can be output and the vehicle cockpit system can be controlled to achieve timely health management of the driver, which greatly improves the efficiency of health management of the driver.

[0019] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present application. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0021] Figure 1 It is a flowchart of a safety warning method for long-term driving shown in an exemplary embodiment of the present application;

[0022] Figure 2 is based on Figure 1 The exemplary embodiment shown is a flow chart of another safety warning method for long-term driving;

[0023] Figure 3 is based on Figure 2 The exemplary embodiment shown is a flow chart of another safety warning method for long-term driving;

[0024] Figure 4 is based on Figure 1 The exemplary embodiment shown is a flow chart of another safety warning method for long-term driving;

[0025] Figure 5 is based on Figure 1 The exemplary embodiment shown is a flow chart of another safety warning method for long-term driving;

[0026] Figure 6 is a schematic structural diagram of a safety warning device for long-term driving shown in an exemplary embodiment of the present application;

[0027] Figure 7 A schematic structural diagram of an embodiment of a computer device provided by the present application is shown. DETAILED DESCRIPTION

[0028] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0031] The term "multiple" as used in this application refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0032] With the development of society, cars have become an indispensable means of transportation in people's daily lives, and driving safety and driver health issues have received more and more attention. Long-term driving can cause physical fatigue and discomfort to drivers, such as back pain, chronic prostate disease, etc. These problems not only affect the driver's driving safety, but may also have a long-term impact on the driver's health. Therefore, how to effectively prevent health problems caused by long-term driving is an urgent problem to be solved in the current fields of automotive health equipment, driving safety equipment, and physical health monitoring equipment.

[0033] The existing solutions are mainly to relieve the driver's fatigue and discomfort by designing various driving assistance devices, such as seat adjusters, massagers, etc. These devices can improve the driver's driving experience to a certain extent, but because the driver needs to operate them by himself, they are often turned on by himself when the driver has obviously felt tired and uncomfortable, resulting in the driver's failure to turn off his own fatigue and discomfort in time, and unable to take timely precautions. Therefore, it cannot fundamentally solve the driver's health problems caused by long-term driving. In addition, there are some health monitoring devices that can monitor the driver's physical condition and detect potential health problems in time, but these devices usually require the driver to operate them by himself, which is inconvenient to use and cannot monitor the driver's health in real time.

[0034] The problems existing in the existing technology in this field are mainly as follows: First, although the existing driving assistance equipment can relieve the driver's fatigue and discomfort, because it requires the driver to operate it by himself, it is often turned on by himself when the driver has obviously felt tired and uncomfortable, resulting in the driver's failure to turn off his own fatigue and discomfort in time, and unable to take timely precautions. Therefore, it cannot fundamentally solve the driver's health problems caused by long-term driving, such as back pain, chronic prostate disease, etc. Secondly, although the existing health monitoring equipment can monitor the driver's physical condition, it requires the driver to operate it by himself, which is inconvenient to use, and cannot monitor the driver's health status in real time. Finally, the existing technical solutions often only focus on driving safety and driver comfort, but ignore the driver's health problems. This is not a sustainable solution.

[0035] Therefore, in order to solve the technical problems existing in the prior art, the present application proposes a safety warning method, device, computer equipment and storage medium for long-term driving to solve the technical problems existing in the prior art mentioned above.

[0036] It should be noted that the implementation of this solution requires the combination of the intelligent health monitoring system, the Internet of Vehicles system, the automatic adjustment of seats and air conditioning system, the healthy diet and rest reminder system, and the intelligent assisted driving system. The executor of this solution is the intelligent cockpit controller, which is connected to the intelligent health monitoring system, the Internet of Vehicles system, the automatic adjustment of seats and air conditioning system, the healthy diet and rest reminder system, and the intelligent assisted driving system.

[0037] Among them, the intelligent health monitoring system is integrated in a fixed position on the steering wheel of the car. It consists of an optical sensor, a face recognition camera sensor and a biomedical signal processing device. Executable operations: Real-time monitoring of the driver's physiological parameters, such as heart rate, blood pressure, body temperature, etc., through optical sensors combined with biomedical signal processing technology; collecting the driver's appearance through a face camera; collecting driving behavior data, such as vehicle speed, braking frequency, steering angle, etc., through a body posture sensor.

[0038] The Internet of Vehicles system, the vehicle-mounted T-BOX (Telematics BOX), integrates a 5G communication module, which can adopt Huawei's 5G communication module. The module has an uplink rate of up to 1Gbps and a downlink rate of up to 2Gbps, and can obtain the driver's health status in real time. The smart cockpit controller exchanges information with the external analysis terminal through the Internet of Vehicles system.

[0039] The automatic adjustment seat and air conditioning system (i.e., the vehicle cockpit system) adjusts the support position and angle of the seat under the control of the intelligent cockpit controller; adjusts the position and intensity of infrared rays, the position, strength, frequency of massage rollers and massage airbags, and the temperature and wind speed of the air conditioning to reduce the driver's fatigue and discomfort, and prevent back pain and chronic prostate disease. The intelligent cockpit controller controls the vehicle cockpit system according to the early warning instructions, that is, it controls the automatic adjustment seat and air conditioning system to adjust the vehicle's seat and air conditioning.

[0040] A healthy diet and rest reminder system is installed inside the car. The system is connected to the intelligent health monitoring system and can recommend a suitable healthy diet plan based on the driver's health status and driving time. It can also remind the driver to take regular breaks through voice or display screens to avoid long-term continuous driving.

[0041] The intelligent assisted driving system can take over the vehicle and park it in a safe area when it receives permission. It can also automatically call the emergency center and provide the driver's health information so that emergency personnel can respond in time.

[0042] The specific implementation of the present application scheme is described in detail by the following embodiments.

[0043] Figure 1 A flowchart of an embodiment of the long-term driving safety warning method of the present application is shown, and the method is executed by a computer device. Figure 1 As shown, the method comprises the following steps:

[0044] S110: Obtain current status information corresponding to the current driver.

[0045] The current status information includes the current driver's physical status information and driving status information, as well as the vehicle driving status information.

[0046] Exemplarily, the physical state information and driving state information in the current state information are obtained by the above-mentioned intelligent health detection system. How the intelligent health detection system specifically collects the driver's physiological parameters, the driver's facial state, and driving behavior data is described in detail in the above introduction to the intelligent health detection system, and will not be repeated here. By analyzing the collected physiological parameters, the driver's facial state, and the driving behavior data of the driver, the current state information representing the driver's health status can be obtained to prepare for the subsequent provision of corresponding warnings and suggestions.

[0047] S120: Determine a state information set corresponding to the current state information in a preset classification model as a target state information set.

[0048] The preset classification model includes a plurality of status information sets, each status information set includes a plurality of historical status information of the same category, and each status information set corresponds to an early warning processing method.

[0049] Exemplarily, the input of the preset classification model is state information, the state information includes historical state information and current state information, and the output of the preset classification model is a state information set. Preferably, there are five state information sets, and the corresponding warning processing methods include no warning processing method, mild warning processing method, moderate warning processing method, severe warning processing method and dangerous warning processing method.

[0050] S130: Outputting a warning instruction according to the warning processing method corresponding to the target state information set, and controlling the output of the warning reminder and the vehicle cockpit system according to the warning instruction.

[0051] Exemplarily, the warning instruction includes outputting a warning reminder and a control strategy for the cockpit system. The preferred warning processing method and the corresponding warning instruction are shown in Table 1 below:

[0052] Table 1 Warning processing methods and corresponding warning instructions

[0053]

[0054]

[0055] As shown in Table 1, the vehicle cabin system includes seats and air conditioning. The therapy mode and air conditioning mode corresponding to the seat therapy and air conditioning systems in Table 1 are the control strategies corresponding to the warning instructions. The warning reminder is given through voice broadcast and / or display on the central control screen.

[0056] This embodiment determines the state information set corresponding to the current state information in the preset classification model as the target state information set according to the current state information corresponding to the current driver, outputs a warning instruction according to the warning processing method corresponding to the target state information set, and controls the output of the warning reminder according to the warning instruction, as well as the control of the vehicle cockpit system. The warning reminder for the driver and the warning operation of controlling the vehicle cockpit system are realized. The whole process does not require manual operation by the driver, and the health warning and management of the driver are automatically realized, avoiding driving safety hazards caused by the driver's physical health.

[0057] At the same time, since the current status information corresponding to the current driver is obtained in real time, and the corresponding warning instructions are also automatically generated in real time, compared with the existing technology that requires the driver to monitor and activate it independently, the safety warning of this solution is more timely and runs through the entire driving process of the driver. It is also more comprehensive, so it can be more preventive and can provide warnings and adjustments before further serious health problems are caused, avoiding poor warning effects caused by intervention after long-term driving.

[0058] Moreover, through the preset classification model, the target state information set corresponding to the current state information can be quickly determined, and the corresponding early warning processing method can be further quickly determined. Then, early warning instructions can be output according to the corresponding early warning processing method, and early warning reminders can be output and the vehicle cabin system can be controlled to realize timely health management of the driver, which greatly improves the efficiency of health management of the driver.

[0059] In some embodiments, how to construct a preset classification model is described in detail. Figure 2 , Figure 2 is based on Figure 1 The exemplary embodiment shown is a flow chart of another long-term driving safety warning method. Figure 1 Based on the S110 to S130 shown, it further includes S210 to S240, which are described in detail as follows:

[0060] S210: Using the body state information, driving state information, and vehicle travel state information as coordinate axes of different dimensions, respectively, to construct an initial coordinate system.

[0061] For example, the example illustrates that the physical state information is used as the X-axis, including heart rate parameters, blood pressure parameters and body temperature parameters, to represent the current driver's physical health; the driving state information is used as the Y-axis, including the driver's fatigue level and concentration level, to represent the current driver's mental state; the vehicle driving state information is used as the Z-axis to represent the current driver's danger level. There is no restriction on which information is used as which coordinate axis, which is only used as an example and is not specifically limited.

[0062] S220: According to the historical status information of the current driver, coordinate points corresponding to each historical status information are drawn in the initial coordinate system.

[0063] The historical status information of the current driver is the status information of the current driver collected historically. Since the status information is used to analyze the physical health information of a single individual, the historical status information can only be based on the status information of a single individual.

[0064] Exemplarily, the historical state information includes historical physical state information, historical driving state information, and historical vehicle driving state information. The coordinate points corresponding to the historical state information are obtained on the initial coordinate system according to the historical physical state information, historical driving state information, and historical vehicle driving state information. When a certain amount of data is collected, n data points can be formed in the three-dimensional coordinate system.

[0065] S230: Determine a plurality of clusters in the initial coordinate system according to the plurality of coordinate points obtained by drawing.

[0066] Each cluster corresponds to a state information set, and the categories of historical state information in the same state information set are the same.

[0067] Exemplarily, k different numbers of clusters are found by mathematically clustering the n data points.

[0068] S240: A preset classification model is constructed according to the initial coordinate system and the multiple clusters, and a corresponding early warning processing method is preset for each cluster.

[0069] Among them, the input of the preset classification model is state information, and the output is a state information set.

[0070] Exemplarily, a preset classification model is constructed based on the initial coordinate system and multiple clusters. A corresponding warning processing method is preset for each cluster, that is, the P data points classified into the same cluster are given a warning prompt through the same combination of warning methods.

[0071] This embodiment uses the body state information, driving state information, and vehicle driving state information as coordinate axes of different dimensions to construct an initial coordinate system, and then plots the historical state information of the current driver in the initial coordinate system to obtain corresponding coordinate points; further determines multiple clusters based on the plotted coordinate points, and finally constructs a preset classification model based on the clusters and the initial coordinate system. This realizes the establishment of a preset classification model based on the historical state information of the current driver, and further improves this technical solution.

[0072] At the same time, by constructing a preset classification model, the corresponding status information set can be quickly determined based on the current status information, and the corresponding early warning processing method can be quickly determined, thereby improving the execution efficiency of the overall plan.

[0073] Furthermore, when establishing the preset classification model, by establishing the initial coordinate system and drawing coordinate points, the preset classification model is fully combined with the current driver's physical state information, driving state information and vehicle travel state information, avoiding the omission of historical state information, and making the obtained clustering clusters more accurate. Therefore, the preset classification model constructed according to the initial coordinate system and clustering clusters is more accurate and comprehensive when classifying the current state information in the subsequent classification, thereby improving the accuracy of the solution.

[0074] In some embodiments, how to determine multiple clusters in the initial coordinate system is described in detail, see Figure 3 , Figure 3 is based on Figure 2 The exemplary embodiment shown is a flow chart of another long-term driving safety warning method. Figure 2 The S230 shown further includes S231 to S232, which are described in detail as follows:

[0075] S231: If the number of coordinate points in the designated spatial region is a preset number, the designated spatial region is used as a designated cluster.

[0076] The specified spatial region is any spatial region of a fixed size in the initial coordinate system.

[0077] For example, the designated space is a spherical space with a preset radius, or a three-dimensional space of other shapes. The three-dimensional coordinate system space can be divided into a plurality of designated space regions to determine the number of coordinate points in each designated space region, and the designated space regions with the number reaching the preset number are regarded as a designated cluster.

[0078] S232: taking the historical state information corresponding to the coordinate points in the designated spatial region as the state information of the same category to form a designated state information set corresponding to the designated cluster, so as to obtain multiple clusters in the initial coordinate system and the state information set corresponding to each cluster.

[0079] Exemplarily, each designated cluster is similar to a data set, and each historical status information therein is taken as status information of the same category, that is, as a subset to constitute a designated status information set corresponding to the corresponding designated cluster, and so on, to determine multiple clusters, and determine the status information set corresponding to each cluster.

[0080] The present embodiment provides a method for determining clustering clusters, which is similar to dividing the three-dimensional coordinate system space and performing data analysis on each designated spatial area, so as to accurately and without omission identify the designated spatial area with a number of coordinate points greater than a preset number as the designated clustering cluster, so as to ensure that the clustering clusters in the entire three-dimensional coordinate system space and the state information set corresponding to each clustering cluster are comprehensively and without omission determined.

[0081] In some embodiments, the preset classification model is a coordinate system with multiple clusters, each cluster corresponding to a corresponding state information set; Figure 4 As shown, it is described in detail how to determine the state information set corresponding to the current state information in the preset classification model as the target state information set. Figure 4 is based on Figure 1 The exemplary embodiment shown is a flow chart of another long-term driving safety warning method. Figure 1 The S120 shown further includes S121 to S122, which are described in detail as follows:

[0082] S121: Determine the target coordinate point corresponding to the current state information in the coordinate system, and calculate the distance value between the target coordinate point and the center of each cluster.

[0083] Among them, each cluster has a center point, and the center distance value is the distance value between the target coordinate point and the center point of each cluster.

[0084] For example, the physical state information, driving state information, and vehicle driving state information in the current state information are digitized, and the three digitized values ​​are respectively corresponded to the three axes in the coordinate system to obtain a coordinate point on the coordinate system, which is the target coordinate point. Combined with the coordinate system, the distance value between the target coordinate point and the center point of each cluster is calculated as the center distance value (here the absolute value is taken), thereby obtaining multiple center distance values.

[0085] S122: taking the cluster corresponding to the minimum center distance value as the target cluster corresponding to the target coordinate point, and taking the state information set represented by the target cluster as the target state information set.

[0086] Among them, the minimum center distance value is the minimum center distance value. The center distance value represents the distance relationship between the target coordinate point and the cluster cluster. The minimum center distance value means that the cluster cluster corresponding to the minimum center distance value is closest to the target coordinate point.

[0087] Exemplarily, the sizes of the center distance values ​​are compared to determine the minimum center distance value, and then the cluster corresponding to the minimum center distance value is used as the target cluster corresponding to the target coordinate point. That is, the cluster closest to the target coordinate point is selected as the corresponding target cluster, and then the state information set corresponding to the target cluster is used as the target state information set to determine the state information set corresponding to the current state information.

[0088] When a new data point is added (i.e., a new target coordinate point is added), it is not necessary to perform calculations to determine which cluster the location of the data point is closest to. The warning combination processing method corresponding to the cluster can be reused to warn the driver and adjust the corresponding seat and air-conditioning system. This can greatly simplify the operation of determining the warning processing method, thereby improving the warning efficiency.

[0089] This embodiment refines the step of determining the state information set corresponding to the current state information in the preset classification model as the target state information set, and further improves the technical solution; by converting the current state information into the target coordinate point in the coordinate system corresponding to the preset classification model, and calculating the center distance value between the target coordinate point and the cluster cluster, the cluster cluster closest to the target coordinate point is determined, thereby quickly determining the state information set corresponding to the current state information. The scheme is converted into a simple mathematical calculation, thereby greatly improving the data processing efficiency of determining the state information set corresponding to the current state information, and further improving the data processing efficiency of the overall scheme. In addition, the mathematical calculation method of calculating the center distance value and comparing the size makes data processing more accurate, thereby improving the accuracy rate.

[0090] In some embodiments, it is described in detail how to handle the situation where there are more than two minimum center distance values. After the cluster corresponding to the minimum center distance value is used as the target cluster corresponding to the target coordinate point in S122 of the method, it also includes: if there are at least two target clusters, the warning processing methods corresponding to the state information sets represented by each target cluster are fused; the fused warning processing methods are deduplicated, and the warning processing method obtained after deduplication is used as the target warning processing method.

[0091] For example, if there are more than two target clusters, it means that there are more than two minimum center distance values, that is, there are more than two minimum and equal center distance values, then there are more than two corresponding state information sets, and then it can be obtained that there is more than one warning processing method corresponding to the state information set. Therefore, it is necessary to enumerate and fuse the corresponding warning processing methods, so as to obtain the fused warning processing method, remove the repeated warning processing methods, and obtain the final warning processing method, which is the target warning processing method.

[0092] This embodiment refines the situation where there is more than one minimum center distance value, and further improves this technical solution. By fusing and removing duplicates of the warning processing methods, a target warning processing method is obtained, thereby making the target warning processing method more accurate and comprehensive.

[0093] In some embodiments, how to determine the target coordinate point corresponding to the current state information in the coordinate system is described in detail, that is, the above S121 further includes S1211 to S1212, which are specifically described as follows:

[0094] S1211: numerically process the physical state information, driving state information, and vehicle driving state information in the current state information to obtain three values.

[0095] Among them, physical state information includes heart rate parameters, blood pressure parameters, and body temperature parameters; driving state information includes fatigue level and concentration level; vehicle driving state information includes posture change information, driving trajectory, turn signal information, and braking frequency.

[0096] For example, after the physical condition information is digitized, a physical health parameter score is obtained. The specific digitization measures are as follows:

[0097] The physical state information includes heart rate parameters, blood pressure parameters, and body temperature parameters. Table 2 below shows the classification of preset heart rate parameters, blood pressure parameters, and body temperature parameters.

[0098] Table 2 Classification table of physical status information

[0099]

[0100] Match the collected heart rate, blood pressure and body temperature values ​​with the above Table 2 to determine the level of the current driver's heart rate, blood pressure and body temperature. Since each level of each parameter corresponds to a score, the heart rate score, blood pressure score and body temperature score can be obtained. Multiply each score with the preset weight according to each score, and add the products to finally get the physical health parameter score. The calculation formula is:

[0101] Physical health parameter score (full score 100 points) = 0.4*heart rate score + 0.4*blood pressure score + 0.2*body temperature score

[0102] Among them, the weight of the heart rate score and the blood pressure score are both 0.4, and the weight of the body temperature score is 0.2.

[0103] After the driving status information is digitized, the driving status score is obtained. The specific digitization measures are as follows:

[0104] The driving status information includes fatigue level and concentration level. Table 3 below shows the corresponding classification levels of the preset fatigue level and concentration level.

[0105] Table 3: Driving status information level table

[0106] Fatigue level Mild fatigue Moderate fatigue Very tired Mental fatigue Concentration Highly concentrated Moderate concentration Mild concentration Not focused

[0107] According to the corresponding levels of the current driver's fatigue level and concentration level, the preset scores of the corresponding levels are obtained, that is, the fatigue level score and the concentration level score are obtained. The fatigue level score and the concentration level score are multiplied by their respective preset weights, and the obtained products are added together to finally obtain the driving status score. The calculation formula is:

[0108] Driving status score (full score 100 points) = 0.5 * fatigue level score + 0.5 * concentration level score, where the weight of the fatigue level score and the weight of the concentration level score are both 0.5.

[0109] After the vehicle driving status information is digitized, the resulting hazard level score is obtained. The specific digitization measures are as follows:

[0110] After obtaining the posture change information, driving trajectory, turn signal information, and braking frequency, it is necessary to determine whether there is lane deviation, whether the driving trajectory is consistent with the turn signal information, whether it is in a sharp turn or the turning radius is too large, and other situations that require the driver to increase driving attention and provide warnings. Correspondingly, the lane deviation score, driving trajectory score, turn signal information score, turning radius score, and braking frequency score are obtained.

[0111] The preset weights of each score are multiplied by each score, and the products are added together to finally obtain the risk level score. The calculation formula is:

[0112] Danger level score (full score 100 points) = 0.3*lane departure score + 0.1*driving trajectory score + 0.1*turn signal information score + 0.2*turn radius score + 0.3*braking frequency score

[0113] The weight of the lane departure score and the braking frequency score are both 0.3, the weight of the driving trajectory score and the turn signal information score are both 0.1, and the weight of the turning radius score is 0.2.

[0114] S1212: Plot points in the coordinate system based on the three values ​​to determine the target coordinate point corresponding to the current state information in the coordinate system.

[0115] Exemplarily, according to the physical health parameter score, driving state score, and danger level score as the values ​​of each axis in the coordinate system, a point in the coordinate system is obtained, and this point is the target coordinate point corresponding to the current state information in the coordinate system. It should be noted that since the coordinate system is obtained according to the initial coordinate system, and the initial coordinate system is established according to the physical state information, driving state information, and vehicle driving state information, as coordinate axes of different dimensions. Therefore, the physical health parameter score corresponds to the value of the coordinate axis where the physical state information is located, the driving state score corresponds to the value of the coordinate axis where the driving state information is located, and the danger level score corresponds to the value of the coordinate axis where the vehicle form state is located.

[0116] This embodiment refines the steps of determining the target coordinate point corresponding to the current state information in the coordinate system, and further improves the technical solution. The physical state information, driving state information, and vehicle driving state information in the current state information are numerically processed to obtain three numerical values, and then points are drawn in the coordinate system based on the three numerical values, thereby determining the target coordinate point corresponding to the current state information in the coordinate system. By numerically processing the information, the corresponding target coordinate point is quickly and accurately drawn in the coordinate system, thereby improving the speed and accuracy of data processing.

[0117] At the same time, when performing numerical processing, the parameters included in each information and the weight ratio of each parameter are fully combined. By multiplying the parameter value with the weight and then summing them up, while fully considering each information including the parameters and combining the weight ratio, the numerical processing is more accurate while ensuring data completeness.

[0118] In some embodiments, how to generate current status information is described in detail. Figure 5 , Figure 5 is based on Figure 1 The exemplary embodiment shown is a flow chart of another long-term driving safety warning method. Figure 1 The S110 shown includes S310 to S330, which are described in detail as follows:

[0119] S310: Determine the physical state information of the current driver according to the collected physiological parameters of the current driver.

[0120] The current driver's physical condition information includes multiple driver's physical health parameters, exemplarily including heart rate parameters, blood pressure parameters, and body temperature parameters.

[0121] For example, the current driver's physical condition information can be obtained based on heart rate parameters, blood pressure parameters, and body temperature parameters.

[0122] S320: Sending the collected facial image frame of the current driver to the external analysis end, so that the external analysis end can determine the driving state information of the current driver based on the facial image frame, and the external analysis end can feed back the driving state information.

[0123] Among them, driving status information includes fatigue level and concentration level.

[0124] Exemplarily, the facial image frame of the current driver collected is sent to the external analysis terminal using the above-mentioned Internet of Vehicles system. The external analysis terminal here can quickly determine the current driver's fatigue and concentration based on the facial image frame through the facial recognition model in the external analysis terminal (wherein the input of the facial recognition model is the facial image frame, and the output is the fatigue level and concentration level). According to Table 3 above, the fatigue level and concentration level in the facial recognition model correspond to their respective levels. The fatigue level and concentration level output by the facial recognition model are then fed back to the vehicle through the Internet of Vehicles system, thereby obtaining driving status information including the fatigue level and concentration level.

[0125] S330: Determine the vehicle driving state information according to the current vehicle posture change information, driving trajectory, turn signal information, and braking frequency.

[0126] Among them, the scenes that produce vehicle posture changes include vehicle turning scenes and vehicle lane changing scenes, so the posture change information is determined according to the vehicle turning angle parameters (broadly speaking, including turning, lane changing, U-turn angle parameters) and the vehicle body stability parameters. These two parameters are conventionally collected by the vehicle body posture sensor. The driving trajectory is determined according to the vehicle speed parameters and vehicle position parameters. These two parameters are collected by sensors, preferably vehicle motion information sensors.

[0127] Exemplarily, the turn signal information and the number of brakes can be directly collected based on the vehicle control data. The corresponding braking frequency can be quickly calculated based on the number of brakes and the statistical period. The posture change information, driving trajectory and braking frequency are process parameters. However, in this step, the time parameters corresponding to the current moment are used to determine the vehicle driving state information. Therefore, for the posture change information, driving trajectory and braking frequency, they are all the posture change information, driving trajectory and braking frequency obtained within the statistical period (or preset duration).

[0128] For example, the braking frequency is a frequency parameter obtained by statistics within a statistical period (or a preset duration), that is, a frequency parameter obtained by statistics within a period of a preset duration from the current moment forward.

[0129] This embodiment explains in detail how to obtain the current state information, thereby improving the technical solution. The specific steps for obtaining the body state information, driving state information and vehicle driving state information are refined, wherein the facial image frame is sent to the external analysis terminal, and then transmitted back after the external analysis terminal determines the driving state information, thereby reducing the amount of data processing, saving data processing costs, and improving the data processing efficiency of the overall solution.

[0130] In some embodiments, the execution of determining driving status information based on facial image frames can also be performed in a local processor. Although the amount of data processing is increased, data omissions due to external data transmission can be avoided, thereby ensuring data accuracy.

[0131] In some embodiments, there are multiple target state information sets; how to output the warning instruction according to the warning processing method corresponding to the target state information set is described in detail, and the above S130 further includes S131 to S132, which are described in detail as follows:

[0132] S131: Fusing the warning processing methods corresponding to each target information set, and deduplicating the fused warning processing methods.

[0133] Exemplarily, the warning processing method is specifically as shown in Table 1 above. When there are multiple target information sets, there are corresponding multiple warning processing methods. It is necessary to merge the multiple existing warning processing methods, that is, simply combine the various warning processing methods together. After fusion, it is also necessary to deduplicate the repeated warning processing methods, and finally obtain non-duplicate warning processing methods.

[0134] The deduplication principle is that for the same type of control strategies, only the most serious or strongest control strategies are retained, which is manifested as: the light ones are absorbed by the heavy ones, and the low-strength ones are absorbed by the high-strength ones.

[0135] Exemplarily, in combination with what is shown in Table 1, an example is given to illustrate that if the warning processing methods included are mild warning and moderate warning, then the warning processing methods obtained by fusion are: control the seat therapy to mild therapy, control the air conditioning system to soothing mode, control the seat therapy to moderate therapy, and control the air conditioning system to comfortable mode. The fused warning processing methods are deduplicated. Then the mild therapy and moderate therapy in the seat therapy are deduplicated, and the soothing mode and comfortable mode in the air conditioning system are deduplicated. When deduplicating, since the degree of moderate therapy is heavier than that of mild therapy, and the intensity of the comfortable mode is higher than that of the soothing mode, after fusion, the seat therapy adopts moderate therapy, and the air conditioning system adopts comfortable mode. Finally, the target warning processing method is: control the seat therapy to adopt moderate therapy, and control the air conditioning system to adopt comfortable mode.

[0136] S132: Outputting a warning instruction according to the fusion warning processing method after deduplication.

[0137] Among them, the warning instruction carries warning text and the mode adjustment strategy of the seat and air conditioning in the vehicle cabin system.

[0138] For example, as shown in the above example, the target warning processing method is: controlling the seat therapy to adopt moderate therapy and controlling the air conditioning system to adopt comfortable mode. The corresponding warning instructions include controlling the seat mode in the vehicle cabin system to be adjusted to moderate therapy mode and the air conditioning mode to be adjusted to comfortable mode.

[0139] This embodiment further refines the situation where, when there are multiple target state information sets, warning instructions are output according to the warning processing methods corresponding to the target state information sets. The target warning processing method is obtained by merging and removing duplicate warning processing methods, thereby making the target warning processing method more accurate and comprehensive.

[0140] In some embodiments, the target state information set is multiple; how to control the output of the warning reminder according to the warning instruction and control the vehicle cockpit system is described in detail, and the above S130 further includes S133, which is described in detail as follows:

[0141] S133: Display and play the warning text, and adjust the seat and air conditioner according to the mode adjustment strategy.

[0142] The warning text is outputted simultaneously by voice playback and screen display to remind the driver more clearly, avoiding the situation where the warning reminder fails to play a prompting role due to unclear prompts caused by the use of a single voice or display prompt method. The seats and air conditioner are adjusted according to the mode adjustment strategy, that is, the seats and air conditioner are controlled accordingly according to the mode adjustment strategy.

[0143] Exemplarily, vision (warning signals pop up on the instrument panel, HUD, central control screen, etc., similar to the automatic driving function), hearing (alarm sounds are emitted by the audio system in the cockpit, headrest speakers, etc.), the warning method can be based on the smart cockpit processor (executing entity) to determine the final current health monitoring assessment for a single warning or a combined warning of at least two warning methods. The specific judgment is described in detail in the above embodiments and will not be repeated here.

[0144] This embodiment refines the steps of controlling the output of warning reminders according to the warning instructions and controlling the vehicle cockpit system, further improving the technical solution. The warning text is output simultaneously in two ways: voice playback and screen display, so as to more clearly remind the driver, avoiding the situation where the warning reminder does not play a prompting role due to unclear prompts caused by the use of a single voice or display prompt method.

[0145] Another aspect of the present application also provides a safety warning device for long-term driving, such as Figure 6 As shown, Figure 6 4 is a schematic diagram of a safety warning device for long-term driving according to an exemplary embodiment of the present application. The safety warning device for long-term driving 400 includes: an information acquisition module 410 , a set determination module 420 and a warning module 430 .

[0146] The information acquisition module 410 is used to acquire the current state information corresponding to the current driver; wherein the current state information includes the physical state information and driving state information of the current driver, and the vehicle driving state information;

[0147] A set determination module 420 is used to determine the state information set corresponding to the current state information in the preset classification model as the target state information set; wherein the preset classification model includes multiple state information sets, each state information set includes multiple historical state information of the same type, and each state information set corresponds to an early warning processing method;

[0148] The warning module 430 is used to output a warning instruction according to the warning processing method corresponding to the target state information set, and control the output of the warning reminder according to the warning instruction, and control the vehicle cockpit system.

[0149] In another exemplary embodiment, the safety warning device 400 for long-term driving also includes: a coordinate system construction unit, which is used to use physical state information, driving state information, and vehicle driving state information as coordinate axes of different dimensions to construct an initial coordinate system; a coordinate point drawing unit, which is used to draw coordinate points corresponding to each historical state information in the initial coordinate system according to the historical state information of the current driver; a cluster determination unit, which is used to determine multiple clusters in the initial coordinate system according to the multiple coordinate points drawn; wherein each cluster corresponds to a state information set, and the categories of historical state information in the same state information set are the same; a model construction unit, which is used to construct a preset classification model based on the initial coordinate system and multiple clusters, and preset a corresponding warning processing method for each cluster.

[0150] In another exemplary embodiment, the safety warning device 400 for long-term driving also includes: a cluster designation unit, which is used to use the designated spatial area as a designated cluster if the number of coordinate points in the designated spatial area is a preset number; wherein the designated spatial area is any spatial area of ​​a fixed size in the initial coordinate system; a state information set construction unit, which is used to use the historical state information corresponding to the coordinate points in the designated spatial area as state information of the same category to form a designated state information set corresponding to the designated cluster, so as to obtain multiple clusters in the initial coordinate system, and a state information set corresponding to each cluster cluster.

[0151] In another exemplary embodiment, the preset classification model is a coordinate system in which there are multiple clusters, and each cluster corresponds to a corresponding state information set; the set determination module 420 further includes: a distance value calculation unit, which is used to determine the target coordinate point corresponding to the current state information in the coordinate system, and calculate the center distance value between the target coordinate point and each cluster; a set determination unit, which is used to use the cluster corresponding to the minimum center distance value as the target cluster corresponding to the target coordinate point, and use the state information set represented by the target cluster as the target state information set.

[0152] In another exemplary embodiment, the distance value calculation unit further includes: a digitization subunit, which is used to digitize the physical state information, driving state information, and vehicle driving state information in the current state information, respectively, to obtain three numerical values; a point drawing subunit, which is used to draw points in the coordinate system based on the three numerical values ​​to determine the target coordinate point corresponding to the current state information in the coordinate system.

[0153] In another exemplary embodiment, the safety warning device 400 for long-term driving also includes: a body state determination unit, which is used to determine the body state information of the current driver based on the collected physiological parameters of the current driver; a driving state determination unit, which is used to send the collected facial image frame of the current driver to the external analysis end, so that the external analysis end can determine the driving state information of the current driver based on the facial image frame, and enable the external analysis end to feedback the driving state information; a driving state determination unit, which is used to determine the vehicle driving state information based on the posture change information, driving trajectory, turn signal information, and braking frequency of the current vehicle.

[0154] In another exemplary embodiment, there are multiple target status information sets; the warning module 430 further includes: a fusion and deduplication unit, which is used to fuse the warning processing methods corresponding to each target information set, and deduplicate the fused warning processing methods; an instruction output unit, which is used to output warning instructions according to the deduplicated fused warning processing methods; wherein the warning instructions carry warning text, and mode adjustment strategies for seats and air conditioners in the vehicle cabin system; a warning processing unit, which is used to display and play the warning text, and adjust the seats and air conditioners according to the mode adjustment strategy.

[0155] Combining the above embodiments, it can be seen that:

[0156] The present invention not only focuses on driving safety and driver comfort, but more importantly, on driver health. By using the technical solution provided by the present invention, health problems caused by long-term driving, such as back pain, chronic prostate disease, etc., can be effectively prevented, thereby comprehensively protecting the driver's health.

[0157] The present invention can not only monitor the physical condition of the driver, but also monitor the health status of the driver in real time. In this way, even when the driver is driving, he can know his health status at any time so as to take measures in time to avoid the aggravation of health problems.

[0158] The present invention can automatically monitor the driver's health status in real time without the need for the driver to operate it, greatly improving the convenience of use. At the same time, the present invention can also be connected with other devices (such as vehicle-mounted computers, smart phones, etc.) to achieve data sharing and analysis, further improving the convenience of use.

[0159] It should be noted that the purpose of the present invention is prevention rather than treatment. Through early detection and intervention, health problems caused by long-term driving can be effectively prevented, thereby achieving the purpose of prevention first, which is impossible with the existing technology.

[0160] It should be noted that the long-term driving safety warning device provided in the above embodiment and the long-term driving safety warning method provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment and will not be repeated here.

[0161] Practicality description: Due to the advanced nature of this technical solution, it can be widely used in application fields such as automobile manufacturing, intelligent driving, and safety warning. First of all, for automobile manufacturers, this technical solution can improve the safety performance of automobiles and increase consumers' willingness to buy, thereby enhancing the market competitiveness of products. Secondly, in the field of intelligent driving, this technical solution can improve the environmental perception and decision-making capabilities of the autonomous driving system through the integration of multi-sensory data, thereby improving the safety and reliability of autonomous driving. Finally, in the field of safety warning, this technical solution can reduce the incidence of traffic accidents and improve road safety through real-time monitoring and warning. Therefore, this technical solution has broad market demand and good application prospects.

[0162] Figure 7 A structural schematic diagram of an embodiment of a computer device of the present application is shown, which shows a structural schematic diagram of a computer system of a computer device suitable for implementing an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the computer device.

[0163] See also Figure 7 As shown, the computer device includes: a controller; a memory for storing one or more programs, and when the one or more programs are executed by the controller, the above-mentioned long-term driving safety warning method is executed.

[0164] Please continue reading Figure 7 As shown, the computer system 500 of the computer device includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, ROM 502 and RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0165] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0166] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0167] Another aspect of the present application further provides a computer-readable storage medium, which stores at least one executable instruction. When the executable instruction is executed on a computer device / equipment, the computer device / equipment executes a safety warning method for long-term driving as in any one of the above-mentioned embodiments.

[0168] This embodiment determines the state information set corresponding to the current state information in the preset classification model as the target state information set according to the current state information corresponding to the current driver, outputs a warning instruction according to the warning processing method corresponding to the target state information set, and controls the output of the warning reminder according to the warning instruction, as well as the control of the vehicle cockpit system. The warning reminder for the driver and the warning operation of controlling the vehicle cockpit system are realized. The whole process does not require manual operation by the driver, and the health warning and management of the driver are automatically realized, avoiding driving safety hazards caused by the driver's physical health.

[0169] At the same time, since the current status information corresponding to the current driver is obtained in real time, and the corresponding warning instructions are also automatically generated in real time, compared with the existing technology that requires the driver to monitor and activate it independently, the safety warning of this solution is more timely and runs through the entire driving process of the driver. It is also more comprehensive, so it can be more preventive and can provide warnings and adjustments before further serious health problems are caused, avoiding poor warning effects caused by intervention after long-term driving.

[0170] Moreover, through the preset classification model, the target state information set corresponding to the current state information can be quickly determined, and the corresponding early warning processing method can be further quickly determined. Then, early warning instructions can be output according to the corresponding early warning processing method, and early warning reminders can be output and the vehicle cabin system can be controlled to realize timely health management of the driver, which greatly improves the efficiency of health management of the driver.

[0171] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, wherein a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0172] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0173] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0174] According to one aspect of an embodiment of the present application, a computer system is also provided, including a central processing unit (CPU), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage portion into a random access memory (RAM), such as executing the method in the above embodiment. In RAM, various programs and data required for system operation are also stored. CPU, ROM and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0175] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., are installed on the drive as needed so that the computer program read therefrom is installed into the storage part as needed.

[0176] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.

[0177] The collection and processing of relevant data in this application should be strictly in accordance with the requirements of relevant national laws and regulations when applied in examples, and the informed consent or separate consent of the personal information subject (or with a legal basis) should be obtained, and subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0178] In this application, the face (or other biometric) recognition technology involved, when the above embodiments of this application are applied to specific products or technologies, the relevant data collection, use and processing processes should comply with national laws and regulations. Before collecting facial information, the information processing rules should be informed and the target object’s separate consent (or legal basis) should be sought, and facial information should be processed in strict accordance with the requirements of laws and regulations and personal information processing rules, and technical measures should be taken to ensure the security of relevant data.

Claims

1. A safety warning method for long-term driving, characterized in that: The method comprises: Acquire current state information corresponding to the current driver; wherein the current state information includes physical state information and driving state information of the current driver, and vehicle driving state information; Determine the state information set corresponding to the current state information in the preset classification model as the target state information set; wherein the preset classification model includes multiple state information sets, each of the state information sets includes multiple historical state information of the same type, and each of the state information sets corresponds to an early warning processing method; Output a warning instruction according to the warning processing method corresponding to the target state information set, and control the output of the warning reminder and the vehicle cabin system according to the warning instruction.

2. The method according to claim 1, characterized in that The method further comprises: The body state information, the driving state information, and the vehicle running state information are respectively used as coordinate axes of different dimensions to construct an initial coordinate system; According to the historical status information of the current driver, coordinate points corresponding to each historical status information are plotted in the initial coordinate system; Determine a plurality of clusters in the initial coordinate system according to the plurality of coordinate points obtained by drawing; wherein each cluster corresponds to a state information set, and the categories of the historical state information in the same state information set are the same; The preset classification model is constructed according to the initial coordinate system and the multiple clusters, and a corresponding early warning processing method is preset for each cluster.

3. The method according to claim 2, characterized in that The step of determining a plurality of clusters in the initial coordinate system according to the plurality of coordinate points obtained by drawing further comprises: If the number of coordinate points in the designated spatial region is a preset number, the designated spatial region is used as a designated cluster; wherein the designated spatial region is any spatial region of a fixed size in the initial coordinate system; The historical state information corresponding to the coordinate points in the designated spatial area is used as the state information of the same category to form a designated state information set corresponding to the designated cluster, so as to obtain multiple clusters in the initial coordinate system and a state information set corresponding to each cluster.

4. The method according to claim 2, characterized in that: The preset classification model is a coordinate system with multiple clusters, each cluster corresponding to a corresponding state information set; The step of determining a state information set corresponding to the current state information in a preset classification model as a target state information set further includes: Determine the target coordinate point corresponding to the current state information in the coordinate system, and calculate the distance value between the target coordinate point and the center of each cluster; The cluster corresponding to the minimum center distance value is used as the target cluster corresponding to the target coordinate point, and the state information set represented by the target cluster is used as the target state information set.

5. The method according to claim 4, characterized in that The step of determining the target coordinate point corresponding to the current state information in the coordinate system further includes: The body state information, the driving state information, and the vehicle running state information in the current state information are numerically processed respectively to obtain three values; Points are plotted in the coordinate system based on the three values ​​to determine the target coordinate point corresponding to the current state information in the coordinate system.

6. The method according to claim 1, characterized in that Before obtaining the current state information corresponding to the current driver, the method further includes: Determining the physical condition information of the current driver according to the collected physiological parameters of the current driver; Sending the collected facial image frame of the current driver to an external analysis terminal, so that the external analysis terminal determines the driving state information of the current driver based on the facial image frame, and enables the external analysis terminal to feed back the driving state information; The vehicle driving status information is determined based on the current vehicle posture change information, driving trajectory, turn signal information, and braking frequency.

7. The method according to claim 1, characterized in that There are multiple sets of target state information; The outputting of the warning instruction according to the warning processing mode corresponding to the target state information set further includes: The warning processing methods corresponding to each target information set are integrated, and the integrated warning processing methods are deduplicated; Outputting a warning instruction according to the deduplicated fusion warning processing method; wherein the warning instruction carries a warning text, and a mode adjustment strategy of a seat and an air conditioner in a vehicle cabin system; The controlling the output of the warning reminder according to the warning instruction and the controlling of the vehicle cockpit system further comprises: The warning text is displayed and played, and the seat and air conditioner are adjusted according to the mode adjustment strategy.

8. A safety warning device for long-term driving, characterized in that: The device comprises: An information acquisition module, used to acquire current state information corresponding to the current driver; wherein the current state information includes the current driver's physical state information and driving state information, and vehicle driving state information; A set determination module, used to determine the state information set corresponding to the current state information in the preset classification model as the target state information set; wherein the preset classification model includes multiple state information sets, each of the state information sets includes multiple historical state information of the same type, and each of the state information sets corresponds to an early warning processing method; The warning module is used to output a warning instruction according to the warning processing method corresponding to the target state information set, and to control the output of the warning reminder according to the warning instruction, and to control the vehicle cabin system.

9. A computer device, characterized in that: include: Controller; A memory for storing one or more programs. When the one or more programs are executed by the controller, the controller implements the long-time driving safety warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one executable instruction, and when the executable instruction is executed on a computer device / equipment, the computer device / equipment executes the operation of the long-time driving safety warning method as described in any one of claims 1 to 7.

Images